Hugging Face's logo

llm-lab
/
CLASP

Automatic Speech Recognition
Model card Files Community
aboots commited on
Commit
d622f31
·
verified ·
1 Parent(s): d1cfdc8

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -1
README.md CHANGED
@@ -32,7 +32,8 @@ To use these models or train your own on custom datasets, please refer to our [G
32
  5. Use these embeddings for tasks like classification or speech retrieval. For speech retrieval, you can load the [LaBSE](https://huggingface.co/sentence-transformers/LaBSE) sentence transformer to compute the cosine similarity between query and speech embeddings.
33
 
34
  ## Architecture Overview
35
- ![image/png](https://cdn-uploads.huggingface.co/production/uploads/64ba58d377dd483716aba098/qnAr3Yim5Cre-qoRbt09s.png)
 
36
 
37
  ## Contributions
38
  1. We introduce CLASP (Contrastive Language-Speech Pretraining), a novel, lightweight, multilingual, multimodal representation designed for audio-text retrieval.
 
32
  5. Use these embeddings for tasks like classification or speech retrieval. For speech retrieval, you can load the [LaBSE](https://huggingface.co/sentence-transformers/LaBSE) sentence transformer to compute the cosine similarity between query and speech embeddings.
33
 
34
  ## Architecture Overview
35
+
36
+ ![image/png](https://cdn-uploads.huggingface.co/production/uploads/64ba58d377dd483716aba098/3Eb-6SXQ6c48jJNZedrsZ.png)
37
 
38
  ## Contributions
39
  1. We introduce CLASP (Contrastive Language-Speech Pretraining), a novel, lightweight, multilingual, multimodal representation designed for audio-text retrieval.